Abstract
We treat documents released under the Dutch Freedom of Information Act as FAIR scientific data and find that they are not findable nor accessible, due to text malformations caused by redaction software. Our aim is to repair these documents. We propose a simple but strong heuristic for detecting wrongly OCRed text segments, and we then repair only these OCR mistakes by prompting a large language model. This makes the documents better findable through full text search, but the repaired PDFs do still not adhere to accessibility standards. Converting them into HTML documents, keeping all essential layout and markup, makes them not only accessible to the visually impaired, but also reduces their size by up to two orders of magnitude. The costs of this way of repairing are roughly one dollar for the 17K pages in our corpus, which is very little compared to the large gains in information quality.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ahmed, F., Luca, E.W.D., Nürnberger, A.: Revised N-gram based automatic spelling correction tool to improve retrieval effectiveness. Polibits 40, 39–48 (2009)
Amrhein, C., Clematide, S.: Supervised OCR error detection and correction using statistical and neural machine translation methods. J. Lang. Technol. Comput. Linguist. (JLCL) 33(1), 49–76 (2018)
Bland, M., Iyer, A., Levchenko, K.: Story beyond the eye: glyph positions break PDF text redaction. arXiv preprint arXiv:2206.02285 (2022)
Booth, C., Shoemaker, R., Gaizauskas, R.: A language modelling approach to quality assessment of OCR’ed historical text. In: Proceedings of the Thirteenth Language Resources and Evaluation Conference (LREC), pp. 5859–5864 (2022)
Data protection commission: redacting documents and records (2021). https://www.dataprotection.ie/sites/default/files/uploads/2021-08/Redacting/%20Documents/%20and/%20Records.pd
Cuper, M.: Examining a multi layered approach for classification of OCR quality without ground truth. Digit. Humanit. Benelux J. 43 (2022)
Erjavec, T., et al.: The Parlamint corpora of parliamentary proceedings. Lang. Resour. Eval. 415–448 (2022)
European commission: a European strategy for data. Technical Report (2020). https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX:52020DC0066
Marx, M.: Woogle dump. Technical Report, DANS (2023), https://doi.org/10.17026/dans-zau-e3rk
Marx, M., Gielissen, T.: Digital weight watching: reconstruction of scanned documents. Int. J. Doc. Anal. Recognit. (IJDAR) 14, 229–239 (2011)
McCowan, I.A., et al.: On the Use of Information Retrieval Measures for Speech Recognition Evaluation. Technical Report, IDIAP (2004)
Rijksoverheid: wet open Overheid (woo) (2023). https://www.rijksoverheid.nl/onderwerpen/wet-open-overheid-woo
Schaefer, R., Neudecker, C.: A two-step approach for automatic OCR post-correction. In: Proceedings of the 4th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pp. 52–57 (2020)
Strange, C., McNamara, D., Wodak, J., Wood, I.: Mining for the meanings of a murder: the impact of OCR quality on the use of digitized historical newspapers. Digit. Hum. Q. 8, 16 p. (2014)
Traub, M.C., Samar, T., Van Ossenbruggen, J., Hardman, L.: Impact of crowdsourcing OCR improvements on retrievability bias. In: Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries, pp. 29–36 (2018)
Turró, M.R.: Are pdf documents accessible? Inf. Technol. Librar. 27(3), 25–43 (2008). https://doi.org/10.6017/ital.v27i3.3246, https://ejournals.bc.edu/index.php/ital/article/view/3246
Wilkinson, M.D., et al.: The FAIR guiding principles for scientific data management and stewardship. Sci. Data 3(1), 1–9 (2016)
Acknowledgements
This research was supported in part by the Netherlands Organization for Scientific Research (NWO) through the ACCESS project grant CISC.CC.016.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
van Heusden, R., Ling, H., Nelissen, L., Marx, M. (2023). Making PDFs Accessible for Visually Impaired Users (and Findable for Everybody Else). In: Alonso, O., Cousijn, H., Silvello, G., Marrero, M., Teixeira Lopes, C., Marchesin, S. (eds) Linking Theory and Practice of Digital Libraries. TPDL 2023. Lecture Notes in Computer Science, vol 14241. Springer, Cham. https://doi.org/10.1007/978-3-031-43849-3_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-43849-3_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43848-6
Online ISBN: 978-3-031-43849-3
eBook Packages: Computer ScienceComputer Science (R0)